Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ColourCloudSky/review-ui-design-skill --skill review-ui-designgit clone --depth 1 https://github.com/ColourCloudSky/review-ui-design-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/colourcloudsky/review-ui-design-skill/review-ui-design)<a href="https://agentmods.dev/skills/colourcloudsky/review-ui-design-skill/review-ui-design"><img src="https://agentmods.dev/badge/skills/colourcloudsky/review-ui-design-skill/review-ui-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/colourcloudsky/review-ui-design-skill/review-ui-design"><img src="https://agentmods.dev/badge/skills/colourcloudsky/review-ui-design-skill/review-ui-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00195 | $0.03639 |
| Opus 5 | $0.00097 | $0.01819 |
| Sonnet 5 | $0.00039 | $0.00728 |
| Haiku 4.5 | $0.00019 | $0.00364 |
Grade A, and why
review-ui-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品 UI 设计评审
目标
把视觉总监、交互专家、设计系统专家和无障碍专家的检查视角合并成一份去重报告。先判断产品目标和信息传达，再检查视觉精度；不要把流行风格当作质量本身。
执行边界
- 默认只读。除非用户明确要求“帮我修改”“直接改 Figma”等写操作，否则不得修改设计稿、Figma 文件或其他内容。
- 用户明确要求修改时，先完成评审并确认修改范围，再加载并遵循相关 Figma 写入 skill。
- 不把截图中无法测量的像素、色值、字体属性写成确定事实。
- 不为了显得专业而制造问题；只报告有证据、能解释影响的问题。
- 不把偶数字号、固定字阶、60-30-10、4/8px 栅格、固定行高或投影公式等经验法则当作普遍判错标准。
评审流程
1. 识别输入与上下文
按输入类型选择证据：
- 单张截图：做视觉快评；检查可见的视觉、控件语义和系统一致性，标记无法验证的交互状态与精确数值。
- 多张截图/流程图：先确认或推断页面顺序，逐屏检查后再合并跨屏流程、反馈、状态和一致性问题。
- Figma 链接：优先使用官方 Figma 只读工具获取目标节点截图和元数据；先评审用户指定节点，范围不明时从链接节点开始。不要调用写入工具。读取能力不可用或失败时，说明限制并请用户提供截图或导出，不根据链接文字猜测设计内容。
- 修改稿/第二轮设计：识别上一轮问题编号和结论，进入增量复评；不要把修改稿当作全新稿件重新编号。上一轮报告不可见时，先请用户补充；无法取得则明确说明并把本轮建立为新基线。
- 设计规范/组件库同时提供：把它作为最高优先级基准，检查偏离是否有业务理由。
尽量识别平台、核心任务、用户类型、屏幕尺寸、设计阶段和业务约束。缺失信息不应阻塞快评；在报告开头列出关键假设，并降低相关结论的置信度。
按以下证据优先级判断：
- 用户明确目标与业务约束
- 已提供的品牌规范、设计系统和组件规范
- 目标平台约定
- WCAG 等可访问性要求
- 通用设计原则与视觉启发
- 当前风格趋势
2. 加载评审知识
- 每次都完整阅读 visual-quality.md，用“形、色、字、质、构”做视觉深查。
- 用户专门评审图标作品、画面包含成组图标，或初检发现图标系统性问题时，完整阅读 icon-quality.md。
- 出现控件、任务流程、表单、状态或多屏设计时，完整阅读 interaction-quality.md。
- 出现多组件、多页面、Figma 元数据、设计规范或明显复用关系时，完整阅读 design-system-quality.md。
- 输出前完整阅读 report-template.md。
- 只有在用户询问规则来源、需要继续扩充知识库或要联网复核最新规范时，阅读 sources.md。
3. 做四轮检查
- 三秒印象：记录第一视觉焦点、主任务是否可见、整体气质是否与产品匹配。
- 结构检查：检查信息层级、分组、阅读动线、密度、关键操作和跨屏流程。
- 细节检查：逐项检查形、色、字、质、构，以及交互和设计系统。
- 反证检查：对每个候选问题追问：
- 这是错误，还是有意的视觉策略？
- 是否有业务、品牌、平台或无障碍理由？
- 修改后会不会破坏已有优势？
- 仅凭当前证据能否确认？
先记录问题，再按根因合并。相同的间距、色值、圆角、图标或组件问题只报告一次，并列出受影响位置。
4. 补充截图证据
有本地图像和代码执行能力时，只对会影响结论的疑点做程序化检查，不机械跑完整套工具：
- 先确认原始分辨率和缩放状态，再查看 2–4 倍局部裁切；低分辨率放大不会产生新证据。
- 用水平或垂直参考线验证重复元素的边缘、基线和间距关系。
- 取色时选择无抗锯齿、无阴影、无透明叠加的稳定区域，并在多个点复核；截图采样仍标为“近似”，源文件属性或设计 Token 才能标为“已确认”。
- 需要判断层级、体量或小尺寸识别时，生成灰度、轻微模糊和实际使用尺寸视图。
- 保留原图不变；所有裁切、参考线和诊断视图都输出为派生文件，并在报告中写明证据方法。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 187 lines · 195 tokens per session scan A 3db3bbcdd74b
review-ui-design is a skill published in the GitHub repository ColourCloudSky/review-ui-design-skill (113 stars, last pushed 1mo ago), licensed MIT. It adds 195 tokens to every session and 3,639 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.